<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Article-Journal | Hao Qin</title><link>https://qinbaigao.github.io/publication_types/article-journal/</link><atom:link href="https://qinbaigao.github.io/publication_types/article-journal/index.xml" rel="self" type="application/rss+xml"/><description>Article-Journal</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 01 Jan 2026 00:00:00 +0000</lastBuildDate><image><url>https://qinbaigao.github.io/media/icon_hu_eee4a95885829ab2.png</url><title>Article-Journal</title><link>https://qinbaigao.github.io/publication_types/article-journal/</link></image><item><title>GGCN: Gait Recognition with Generate Network and Convolutional Neural Network</title><link>https://qinbaigao.github.io/publications/ggcn/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://qinbaigao.github.io/publications/ggcn/</guid><description>&lt;p&gt;GGCN targets robust gait recognition under multiple covariates by separating low-level feature extraction, encoding, and feature mapping.&lt;/p&gt;</description></item><item><title>Distilling Multi-view Diffusion Models into 3D Generators</title><link>https://qinbaigao.github.io/publications/dd3g/</link><pubDate>Thu, 03 Apr 2025 00:00:00 +0000</pubDate><guid>https://qinbaigao.github.io/publications/dd3g/</guid><description>&lt;p&gt;DD3G transfers visual and spatial knowledge from a multi-view diffusion model into an efficient feed-forward 3D Gaussian generator.&lt;/p&gt;</description></item><item><title>Progressive Semantic Learning for Unsupervised Skeleton-based Action Recognition</title><link>https://qinbaigao.github.io/publications/prosl/</link><pubDate>Thu, 06 Feb 2025 00:00:00 +0000</pubDate><guid>https://qinbaigao.github.io/publications/prosl/</guid><description>&lt;p&gt;ProSL uses cluster-level semantic information to improve self-supervised skeleton representation learning beyond instance-level contrastive objectives.&lt;/p&gt;</description></item><item><title>Semantic-aware Contrastive Learning via Multi-prompt Alignment</title><link>https://qinbaigao.github.io/publications/sacl/</link><pubDate>Thu, 06 Feb 2025 00:00:00 +0000</pubDate><guid>https://qinbaigao.github.io/publications/sacl/</guid><description>&lt;p&gt;The paper investigates how semantic consistency in generated positive samples affects representation learning.&lt;/p&gt;</description></item><item><title>MFNet: Multi-Feature Fusion Network for Real-Time Semantic Segmentation in Road Scenes</title><link>https://qinbaigao.github.io/publications/mfnet/</link><pubDate>Tue, 01 Nov 2022 00:00:00 +0000</pubDate><guid>https://qinbaigao.github.io/publications/mfnet/</guid><description>&lt;p&gt;MFNet is designed for practical real-time semantic segmentation, reaching strong accuracy-speed tradeoffs on road-scene benchmarks.&lt;/p&gt;</description></item><item><title>RPNet: Gait Recognition with Relationships Between Each Body-Parts</title><link>https://qinbaigao.github.io/publications/rpnet/</link><pubDate>Sun, 01 May 2022 00:00:00 +0000</pubDate><guid>https://qinbaigao.github.io/publications/rpnet/</guid><description>&lt;p&gt;RPNet studies how relationships among body parts can improve gait recognition under challenging covariates.&lt;/p&gt;</description></item></channel></rss>